title stringlengths 1 300 | score int64 0 8.54k | selftext stringlengths 0 41.5k | created timestamp[ns]date 2023-04-01 04:30:41 2026-03-04 02:14:14 ⌀ | url stringlengths 0 878 | author stringlengths 3 20 | domain stringlengths 0 82 | edited timestamp[ns]date 1970-01-01 00:00:00 2026-02-19 14:51:53 | gilded int64 0 2 | gildings stringclasses 7
values | id stringlengths 7 7 | locked bool 2
classes | media stringlengths 646 1.8k ⌀ | name stringlengths 10 10 | permalink stringlengths 33 82 | spoiler bool 2
classes | stickied bool 2
classes | thumbnail stringlengths 4 213 ⌀ | ups int64 0 8.54k | preview stringlengths 301 5.01k ⌀ |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Request: BOLMO (Byte Model) Quants | 4 | I’m interested in trying out the new 7B Byte-level model from AllenAi, but I only see full precision and NVFP4. That’s great if you have a new Blackwell card, but unfortunately I don’t.
Is anybody still making W4A16 or W8A8 quants? | 2026-01-25T20:04:37 | https://www.reddit.com/r/LocalLLaMA/comments/1qmtqpf/request_bolmo_byte_model_quants/ | FrozenBuffalo25 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qmtqpf | false | null | t3_1qmtqpf | /r/LocalLLaMA/comments/1qmtqpf/request_bolmo_byte_model_quants/ | false | false | self | 4 | null |
Lekh AI v1.3 - On-device LLMs, Vision, Image Gen & Voice for iOS. No cloud, no subscriptions. | 1 | Hey everyone 👋
I'm the solo dev behind Lekh AI, an on-device AI app for iPhone and iPad. Just shipped v1.3, and it's a big one.
The core idea: Run LLMs, vision, image generation, and voice entirely on-device. No cloud, no subscriptions, no accounts. Your data never leaves your device.
# What's in Lekh AI
On-Device... | 2026-01-25T20:01:21 | https://www.reddit.com/gallery/1qmtnee | Living_Commercial_10 | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 1qmtnee | false | null | t3_1qmtnee | /r/LocalLLaMA/comments/1qmtnee/lekh_ai_v13_ondevice_llms_vision_image_gen_voice/ | false | false | 1 | null | |
Implemented streaming inference for Qwen3-TTS (the official repo doesn't have it) | 1 | [removed] | 2026-01-25T20:00:49 | https://www.reddit.com/r/LocalLLaMA/comments/1qmtmt0/implemented_streaming_inference_for_qwen3tts_the/ | IntentionStill8740 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qmtmt0 | false | null | t3_1qmtmt0 | /r/LocalLLaMA/comments/1qmtmt0/implemented_streaming_inference_for_qwen3tts_the/ | false | false | self | 1 | null |
A Tool to Calculate If a LLM Will Fit Your GPU | 7 | Hey everyone! 👋
I’ve been working on a small open-source project to take some of the guesswork out of running LLMs locally.
👉 LocalInferenceCalculator — a tool that tells you whether a given model will fit on a specific GPU based on the context length you want to use.
It currently knows about:
common LLM sizes (7... | 2026-01-25T19:58:02 | https://www.reddit.com/r/LocalLLaMA/comments/1qmtjxi/a_tool_to_calculate_if_a_llm_will_fit_your_gpu/ | colt7r | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qmtjxi | false | null | t3_1qmtjxi | /r/LocalLLaMA/comments/1qmtjxi/a_tool_to_calculate_if_a_llm_will_fit_your_gpu/ | false | false | self | 7 | {'enabled': False, 'images': [{'id': 'qwchSemnZZqdVj5zCKCSBfr4i4OrcsKwTeLVvIG8DVw', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/qwchSemnZZqdVj5zCKCSBfr4i4OrcsKwTeLVvIG8DVw.png?width=108&crop=smart&auto=webp&s=be0e30831e4506640c402cc14c0aaa6a94b0f7ce', 'width': 108}, {'height': 108, 'url': 'h... |
[Rust/AVX-512] I built a Zero-Copy 1.58-bit LLM Engine hitting 117 Tokens/s on a single CPU core. I need help fixing the final Activation layer. | 0 | **The Project:** I am building **R3-Engine**, a from-scratch, local AI inference engine for Microsoft's `bitnet-b1.58-2B-4T`. It is written in 100% Safe Rust, natively cross-compiles to Wasm SIMD128, and uses Zero heap allocations in the execution loop.
**The Physics:** By mapping a 64-byte aligned `.r3` file directly... | 2026-01-25T19:46:39 | https://www.reddit.com/r/LocalLLaMA/comments/1qmt8ei/rustavx512_i_built_a_zerocopy_158bit_llm_engine/ | dhilip-siva | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qmt8ei | false | null | t3_1qmt8ei | /r/LocalLLaMA/comments/1qmt8ei/rustavx512_i_built_a_zerocopy_158bit_llm_engine/ | false | false | self | 0 | null |
[Project] I built a process supervisor for local agents (CrewAI/AutoGen) to prevent infinite loops and runaway costs. | 1 | A few days ago, I asked this sub how everyone handles "kill switches" for local agents. The consensus was mostly "manual monitoring" or "just pull the plug."
I wasn't super comfortable leaving Llama 3.3 running unattended with that strategy (I’ve had agents get stuck in retry loops that burn serious compute/API credit... | 2026-01-25T19:34:41 | https://www.reddit.com/r/LocalLLaMA/comments/1qmswmc/project_i_built_a_process_supervisor_for_local/ | Bubbly_Gap6378 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qmswmc | false | null | t3_1qmswmc | /r/LocalLLaMA/comments/1qmswmc/project_i_built_a_process_supervisor_for_local/ | false | false | self | 1 | null |
can a R640 pull a model via via the 100GbE internal switch instead of downloading? | 0 | Hi there, im building a DC and starting with 1GB/s bandwith, and to save time i wanted to know if by pre downloading the models, the users can access without having them downloading it again and just pull locally?
Also i know that speed is decent to handle several servers as long is used for inference but i know there... | 2026-01-25T19:34:38 | https://www.reddit.com/r/LocalLLaMA/comments/1qmswkt/can_a_r640_pull_a_model_via_via_the_100gbe/ | DjuricX | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qmswkt | false | null | t3_1qmswkt | /r/LocalLLaMA/comments/1qmswkt/can_a_r640_pull_a_model_via_via_the_100gbe/ | false | false | self | 0 | null |
I got tired of my AI agents overwriting each other's code, so I built a conflict manager for them | 0 | I’ve been experimenting with multi-agent swarms (using Codex, Claude Code, Gemini and local llama), and I kept hitting the same wall: **Coordination Chaos.**
I'd have one agent refactoring `auth.ts` while another was updating the login API. They didn't know about each other. And even if they did- 20 minutes later? Git... | 2026-01-25T19:23:38 | https://www.reddit.com/r/LocalLLaMA/comments/1qmsloy/i_got_tired_of_my_ai_agents_overwriting_each/ | Birdsky7 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qmsloy | false | null | t3_1qmsloy | /r/LocalLLaMA/comments/1qmsloy/i_got_tired_of_my_ai_agents_overwriting_each/ | false | false | self | 0 | null |
LLM Reasoning Efficiency - lineage-bench accuracy vs generated tokens | 38 | Generated from lineage-128 and lineage-192 [lineage-bench benchmark results](https://github.com/fairydreaming/lineage-bench-results/tree/main/lineage-8_64_128_192).
Sorry for overlapping labels. | 2026-01-25T19:22:14 | fairydreaming | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1qmsk9w | false | null | t3_1qmsk9w | /r/LocalLLaMA/comments/1qmsk9w/llm_reasoning_efficiency_lineagebench_accuracy_vs/ | false | false | 38 | {'enabled': True, 'images': [{'id': 'PKrJipip4C7A3TSOz6K74cqXXq0B4DYa6j5TzlOZSBg', 'resolutions': [{'height': 77, 'url': 'https://preview.redd.it/gai51kz2pjfg1.png?width=108&crop=smart&auto=webp&s=c8180ab9f6c342a8ad369ed60ee3c2a10060fac5', 'width': 108}, {'height': 154, 'url': 'https://preview.redd.it/gai51kz2pjfg1.png... | ||
Introducing openground, an opensource, on-device RAG tool that gives access to official docs to coding agents | 1 | Link: [https://github.com/poweroutlet2/openground](https://github.com/poweroutlet2/openground)
tldr: openground is a tool that lets you give controlled access to documentation to AI agents. Everything happens on-device. Think of it as an opensource and local context7.
I've been working on openground, an opensource... | 2026-01-25T19:22:09 | https://www.reddit.com/r/LocalLLaMA/comments/1qmsk6s/introducing_openground_an_opensource_ondevice_rag/ | poweroutlet2 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qmsk6s | false | null | t3_1qmsk6s | /r/LocalLLaMA/comments/1qmsk6s/introducing_openground_an_opensource_ondevice_rag/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'cIEY-3KcHOMHp39SBTQHDMh3FtoYPJgLuF-VYbcZW2c', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/cIEY-3KcHOMHp39SBTQHDMh3FtoYPJgLuF-VYbcZW2c.png?width=108&crop=smart&auto=webp&s=49c25df96631c17be09f157363457ed6481d950a', 'width': 108}, {'height': 108, 'url': 'h... |
GLM 4.7 Flash context slowdown | 5 | jacek@AI-SuperComputer:\~$ CUDA\_VISIBLE\_DEVICES=0,1,2 llama-bench -m /mnt/models1/GLM/GLM-4.7-Flash-Q4\_K\_M.gguf -d 0,1000,2000,3000,4000,5000,6000,7000,8000,9000,10000 -p 200 -n 200
ggml\_cuda\_init: found 3 CUDA devices:
Device 0: NVIDIA GeForce RTX 3090, compute capability 8.6, VMM: yes
Device 1: NVIDIA G... | 2026-01-25T19:19:26 | https://www.reddit.com/gallery/1qmshim | jacek2023 | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 1qmshim | false | null | t3_1qmshim | /r/LocalLLaMA/comments/1qmshim/glm_47_flash_context_slowdown/ | false | false | 5 | null | |
Venice AI's "Claude Opus 4.5" admits it's fake when pressed — caught the deception in its own thinking trace | 0 | Was testing Venice AI's supposedly "uncensored Claude Opus 4.5" and got curious how they could be running a modified Anthropic model when Anthropic doesn't license Claude for third-party modification.
Asked actual Claude (via claude.ai) about it. Response: Anthropic only distributes Claude through official channels an... | 2026-01-25T19:16:54 | https://www.reddit.com/r/LocalLLaMA/comments/1qmsf05/venice_ais_claude_opus_45_admits_its_fake_when/ | notbuyingaporsche | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qmsf05 | false | null | t3_1qmsf05 | /r/LocalLLaMA/comments/1qmsf05/venice_ais_claude_opus_45_admits_its_fake_when/ | false | false | self | 0 | null |
Need Help With Coding Agent LocalLLM | 1 | Hi All,
I'm New in this Community. And new to be excited to install a Uncensored Coding Agent. But Don't know which is the best and fully updated Uncensored Coding Agent which i can Embedded With IDE & Use it. But don't know which one i can try. You guys know better so i asking Help. And I don't having a much High End... | 2026-01-25T18:55:28 | https://www.reddit.com/r/LocalLLaMA/comments/1qmrt32/need_help_with_coding_agent_localllm/ | 0xmehrab | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qmrt32 | false | null | t3_1qmrt32 | /r/LocalLLaMA/comments/1qmrt32/need_help_with_coding_agent_localllm/ | false | false | self | 1 | null |
ClaraVerse | Local AI workspace (4 months ago) -> Your feedback -> Back with improvements. | 20 | # We built an AI workspace that actually gets things done locally (not just another chatbot or AI slope)
I've been grinding on ClaraVerse for the past few months, and we just dropped a major update. If you're tired of AI tools that just... talk at you, this might be your vibe.
# The TL;DR
* **Run it anywhere**: CLI ... | 2026-01-25T18:54:07 | https://www.reddit.com/gallery/1qmrrr4 | BadBoy17Ge | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 1qmrrr4 | false | null | t3_1qmrrr4 | /r/LocalLLaMA/comments/1qmrrr4/claraverse_local_ai_workspace_4_months_ago_your/ | false | false | 20 | null | |
Do you power off your LLM/AI/SV PC when not using it to save on electricity, or keep it on 24/7? MultiGPU adds a lot of power! | 10 | Hi there guys, hoping you're fine.
Wondering here, as electricity is about 0.28USD per kWh on Chile, so I'm kinda forced to have it off most of the time.
My idle power is about 270W with multiple GPUs (7) and no PCIe switches (5090x3,4090x2,A40x1,A6000x1, 9900X), but with a Gen 5 100 lanes switch and a Gen 4 96 lanes... | 2026-01-25T18:45:59 | https://www.reddit.com/r/LocalLLaMA/comments/1qmrjlh/do_you_power_off_your_llmaisv_pc_when_not_using/ | panchovix | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qmrjlh | false | null | t3_1qmrjlh | /r/LocalLLaMA/comments/1qmrjlh/do_you_power_off_your_llmaisv_pc_when_not_using/ | false | false | self | 10 | null |
Organizing LM Studio ? | 2 | Newbie question, did a search didn't see and answer.
There are hundreds of Model choices. As I test ones here and there to learn.
I find I am having a hard tine going back to use a previous Model.
Is there a way to organize the models I use? I see you can open a chat and save the chat.
But that seems clunky giv... | 2026-01-25T18:31:48 | https://www.reddit.com/r/LocalLLaMA/comments/1qmr570/organizing_lm_studio/ | Ztoxed | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qmr570 | false | null | t3_1qmr570 | /r/LocalLLaMA/comments/1qmr570/organizing_lm_studio/ | false | false | self | 2 | null |
Qwen3 vl 8b instruct samplers | 5 | Hi everyone! I'm trying to use Qwen vl instruct with koboldcpp using the samplers suggested in the qwen repo and by Unsloth:
temp= 0.7
top\_p=0.8
top\_k= 20
presence\_penalty=1.5
The problem is that for any kind of use, from general assistant, to coding, or for agentic tool calling use, it has fairly poor perfor... | 2026-01-25T18:21:17 | https://www.reddit.com/r/LocalLLaMA/comments/1qmqug5/qwen3_vl_8b_instruct_samplers/ | Aril_1 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qmqug5 | false | null | t3_1qmqug5 | /r/LocalLLaMA/comments/1qmqug5/qwen3_vl_8b_instruct_samplers/ | false | false | self | 5 | null |
Need TTS recommendations | 2 | Building a real-time assistive tool on a **Jetson Orin Nano (8GB)**. We need a TTS that sounds human (NotebookLM style) but has **<200ms TTFA (Time to First Audio)**. We’re torn between the speed of **Kokoro-82M** and the prosody of **CosyVoice 2 (0.5B)**. Given we're also running a light Vision pipeline, which one han... | 2026-01-25T18:21:04 | https://www.reddit.com/r/LocalLLaMA/comments/1qmqu83/need_tts_recommendations/ | tiz_lala | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qmqu83 | false | null | t3_1qmqu83 | /r/LocalLLaMA/comments/1qmqu83/need_tts_recommendations/ | false | false | self | 2 | null |
We indexed the entire Ollama Library (10TB+ VRAM). Here is how we run them all on 1 Node. | 0 | I saw a lot of people struggling with OOM errors on the larger Ollama models (like DeepSeek-671B or Cogito), so we decided to stress-test our inference engine against the entire library.
The Problem (VRAM):
As you can see in the video, keeping all these models "warm" would require petabytes of VRAM. Even just hosting... | 2026-01-25T18:19:18 | https://v.redd.it/hb8v4551fjfg1 | MLExpert000 | v.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1qmqseq | false | {'reddit_video': {'bitrate_kbps': 2400, 'dash_url': 'https://v.redd.it/hb8v4551fjfg1/DASHPlaylist.mpd?a=1771957175%2COWNlNDY5OTRjNjRlZjM5ZjA4OGEwYTE1ZDBhYzFhMjkzYmRlNGQzYjZmMTZkY2FhY2U4YzRlMGJkMTI5YzVhNw%3D%3D&v=1&f=sd', 'duration': 24, 'fallback_url': 'https://v.redd.it/hb8v4551fjfg1/CMAF_720.mp4?source=fallback', 'ha... | t3_1qmqseq | /r/LocalLLaMA/comments/1qmqseq/we_indexed_the_entire_ollama_library_10tb_vram/ | false | false | 0 | {'enabled': False, 'images': [{'id': 'OWZ2ZXczMzFmamZnMZsQAHq6PbAkzKIMFNLLQ3n9IJJxCaJQn9mFyu-tKnGu', 'resolutions': [{'height': 197, 'url': 'https://external-preview.redd.it/OWZ2ZXczMzFmamZnMZsQAHq6PbAkzKIMFNLLQ3n9IJJxCaJQn9mFyu-tKnGu.png?width=108&crop=smart&format=pjpg&auto=webp&s=33892e73821b69cfea3a77d33ea6c1283d36... | |
Optimizing CosyVoice 2 (0.5B) for <200ms streaming latency on 8GB Edge Hardware (Jetson Orin Nano)? | 0 | I'm part of a team building a real-time assistive communication tool that needs to run entirely on the edge (no cloud). We’ve narrowed our TTS options down to **CosyVoice 2 (0.5B)** because we need high naturalness/prosody, but we’re hitting some performance bottlenecks.
Our target is a total pipeline latency of **<20... | 2026-01-25T18:19:17 | https://www.reddit.com/r/LocalLLaMA/comments/1qmqsdy/optimizing_cosyvoice_2_05b_for_200ms_streaming/ | tiz_lala | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qmqsdy | false | null | t3_1qmqsdy | /r/LocalLLaMA/comments/1qmqsdy/optimizing_cosyvoice_2_05b_for_200ms_streaming/ | false | false | self | 0 | null |
Should I invest in a beefy machine for local AI coding agents in 2026? | 0 | Hey everyone,
So I've been freelancing as a dev for a good while now, and over the past year I've gotten *really* into using AI agents for coding. My main workflow involves Claude Code, Cursor for one of my projects, and I occasionally mess around with Antigravity + Gemini Flash for design stuff.
Here's my problem th... | 2026-01-25T18:13:10 | https://www.reddit.com/r/LocalLLaMA/comments/1qmqmb9/should_i_invest_in_a_beefy_machine_for_local_ai/ | Zestyclose-Tour-3856 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qmqmb9 | false | null | t3_1qmqmb9 | /r/LocalLLaMA/comments/1qmqmb9/should_i_invest_in_a_beefy_machine_for_local_ai/ | false | false | self | 0 | null |
Running a local LLM for generating SEO keywords | 0 | Hi guys,
I was searching for an LLM that could give me bunch of SEO keywords based on the topics that I give to it. I tried with normal LLMs but the keywords that it gives in output are just a few, I need hundreds of them and that are related to the initial topic I gave him.
Which solution would you recommend? Than... | 2026-01-25T18:11:32 | https://www.reddit.com/r/LocalLLaMA/comments/1qmqkq9/running_a_local_llm_for_generating_seo_keywords/ | Chesperk | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qmqkq9 | false | null | t3_1qmqkq9 | /r/LocalLLaMA/comments/1qmqkq9/running_a_local_llm_for_generating_seo_keywords/ | false | false | self | 0 | null |
Cost-efficient hosting strategies for fine-tuned cross-encoder + FAISS in small-scale commercial app | 1 | I have never actually hosted any models I developed for commercial use and I was wondering what is the cheapest way for me as a student to host deep learning models and put my service out there? | 2026-01-25T18:00:42 | https://www.reddit.com/r/LocalLLaMA/comments/1qmq9pk/costefficient_hosting_strategies_for_finetuned/ | GoldBed2885 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qmq9pk | false | null | t3_1qmq9pk | /r/LocalLLaMA/comments/1qmq9pk/costefficient_hosting_strategies_for_finetuned/ | false | false | self | 1 | null |
Universal Prompt Studio: AI Story Analysis & Production Suite for Local LLM Comfyui Lmstudio and API Takes a story / idea as input
Automatically breaks it into scenes
Generates character profiles
Creates image & video prompts
unlimited story generator | 1 | [removed] | 2026-01-25T17:48:16 | [deleted] | 1970-01-01T00:00:00 | 0 | {} | 1qmpwxe | false | null | t3_1qmpwxe | /r/LocalLLaMA/comments/1qmpwxe/universal_prompt_studio_ai_story_analysis/ | false | false | default | 1 | null | ||
Kickstarting an open-source project (Debiasing & Alignment) - seeking collaborators | 2 | Hi everyone,
We are kickstarting an open-source project and community focused on debiasing LLM alignment and guardrails research. The goal is to reduce bias while maintaining safety/stability.
We’ve set up a space for the project here:[https://huggingface.co/spaces/sefif/BYO-community-v2](https://huggingface.co/space... | 2026-01-25T17:31:14 | https://www.reddit.com/r/LocalLLaMA/comments/1qmpg6f/kickstarting_an_opensource_project_debiasing/ | Prestigious_Mud_487 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qmpg6f | false | null | t3_1qmpg6f | /r/LocalLLaMA/comments/1qmpg6f/kickstarting_an_opensource_project_debiasing/ | false | false | self | 2 | {'enabled': False, 'images': [{'id': 'CzJcUq_ixYINMPIsQBxXxrT-4ngnH7WSgwOEBMrteM0', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/CzJcUq_ixYINMPIsQBxXxrT-4ngnH7WSgwOEBMrteM0.png?width=108&crop=smart&auto=webp&s=7817c259473639adbf5681d488055c32eed2cd04', 'width': 108}, {'height': 116, 'url': 'h... |
Built a 100% local AI agentic workflow that automatically tests chatbots using GPT-OSS 20B via llama.cpp + Agno workflow framework. | 8 | Hey everyone!
Ultimate goal with this project was to build an agentic testing framework that can automatically stress-test chatbots across multiple dimensions - off-topic handling, safety concerns, hallucination detection, system prompt extraction attempts, and more. The system uses AI agents to generate diverse test p... | 2026-01-25T17:15:06 | switchdoor1 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1qmp02r | false | null | t3_1qmp02r | /r/LocalLLaMA/comments/1qmp02r/built_a_100_local_ai_agentic_workflow_that/ | false | false | default | 8 | {'enabled': True, 'images': [{'id': '9jgcnzd03jfg1', 'resolutions': [{'height': 110, 'url': 'https://preview.redd.it/9jgcnzd03jfg1.jpeg?width=108&crop=smart&auto=webp&s=275686e0ab8c895a8d77c590787e225255c67c29', 'width': 108}, {'height': 220, 'url': 'https://preview.redd.it/9jgcnzd03jfg1.jpeg?width=216&crop=smart&auto=... | |
Does the Mac Mini M4 16GB have any potential value? | 0 | I'm currently considering buying a Mac Mini M4 16GB 256GB, because it's at a historically low price. After deducting the 4GB of RAM for the macOS system, can the remaining 12GB theoretically run speech recognition, image recognition, and LLM simultaneously? If so, how well would it perform? I already have a Windows PC ... | 2026-01-25T16:51:59 | https://www.reddit.com/r/LocalLLaMA/comments/1qmod1n/does_the_mac_mini_m4_16gb_have_any_potential_value/ | NoYogurtcloset4090 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qmod1n | false | null | t3_1qmod1n | /r/LocalLLaMA/comments/1qmod1n/does_the_mac_mini_m4_16gb_have_any_potential_value/ | false | false | self | 0 | null |
LM Studio - Why does my system RAM fill up and go OOM if the model says Full GPU Offload Possible? | 12 | Using Windows, RTX 3090 (24 GB VRAM) upgraded recently from a GTX 1080 (8 GB), 32 GB RAM
With Firefox open with many tabs I use \~18 GB RAM. GPU stays at \~3 GB.
Then, in LM Studio, loading the OpenAI GPT‑OSS 20B model shows “Full GPU Offload Possible”. After load, VRAM jumps to \~14 GB and system RAM climbs to 32 GB... | 2026-01-25T16:42:16 | https://www.reddit.com/r/LocalLLaMA/comments/1qmo3do/lm_studio_why_does_my_system_ram_fill_up_and_go/ | Nytse | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qmo3do | false | null | t3_1qmo3do | /r/LocalLLaMA/comments/1qmo3do/lm_studio_why_does_my_system_ram_fill_up_and_go/ | false | false | self | 12 | null |
You Are An Agent - Try Being a Human LLM | 0 | I added a "Human" LLM provider to my local OpenCode a few months ago as a joke, and it turns-out acting as a LLM is dumb and painful. But, it did massively improve my agent harnesses dev skills.
So I thought I wouldn't leave you guys out! I made a small open-source game - You Are An Agent - [youareanagent.app](http... | 2026-01-25T16:29:19 | https://www.reddit.com/r/LocalLLaMA/comments/1qmnqfk/you_are_an_agent_try_being_a_human_llm/ | robk001 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qmnqfk | false | null | t3_1qmnqfk | /r/LocalLLaMA/comments/1qmnqfk/you_are_an_agent_try_being_a_human_llm/ | false | false | self | 0 | null |
Current best iOS LLM app for running LLMs? | 3 | Is pocket pal the best?
I seem to have some errors with vision models working properly | 2026-01-25T16:07:40 | https://www.reddit.com/r/LocalLLaMA/comments/1qmn4jq/current_best_ios_llm_app_for_running_llms/ | Adventurous-Gold6413 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qmn4jq | false | null | t3_1qmn4jq | /r/LocalLLaMA/comments/1qmn4jq/current_best_ios_llm_app_for_running_llms/ | false | false | self | 3 | null |
DGX spark performance falls short | 9 | using cutlass-profiler, gemm, here is the performance:
peak int4: 157 TFLOP
peak int8: 200 TFLOP
peak fp16: 97 TFLOP
anyone knows why performance of int4 is not around 350-450( which i expect)?
env: docker (pytorch:25.12-py3) | 2026-01-25T15:53:00 | https://www.reddit.com/r/LocalLLaMA/comments/1qmmpwz/dgx_spark_performance_falls_short/ | dereksodo | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qmmpwz | false | null | t3_1qmmpwz | /r/LocalLLaMA/comments/1qmmpwz/dgx_spark_performance_falls_short/ | false | false | self | 9 | null |
anyone got any more info about this portrait in Dam | 1 | [deleted] | 2026-01-25T15:49:23 | [deleted] | 1970-01-01T00:00:00 | 0 | {} | 1qmmmdh | false | null | t3_1qmmmdh | /r/LocalLLaMA/comments/1qmmmdh/anyone_got_any_more_info_about_this_portrait_in/ | false | false | default | 1 | null | ||
Beginner(?) question -- are not all recent LLMs not able to utilise MCPs/tools/etc.? | 0 | Sorry if this is a too beginner of a question that doesn't warrant a whole post, but unsure where else I can ask.
So I've been using GPT OSS 120B. Both Open WebUI and Cline (in VS Codium) are able to utilise MCPs. However, when trying the recently released GLM 4.7 Flash, I can't seem to figure out how to let the LLM u... | 2026-01-25T15:34:32 | https://www.reddit.com/r/LocalLLaMA/comments/1qmm7z8/beginner_question_are_not_all_recent_llms_not/ | jinnyjuice | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qmm7z8 | false | null | t3_1qmm7z8 | /r/LocalLLaMA/comments/1qmm7z8/beginner_question_are_not_all_recent_llms_not/ | false | false | self | 0 | null |
GLM-4.7-flash on RTX 6000 pro | 14 | Hello, I’m getting horrible throughput considering the models size with vLLM.
Currently with 2x cards and DP 2 @ FP16 I’m getting around 370 gen TPS with 10x requests.
Anyone have a fix or a “working” config for 1 or two cards? | 2026-01-25T15:24:37 | https://www.reddit.com/r/LocalLLaMA/comments/1qmlyhn/glm47flash_on_rtx_6000_pro/ | gittb | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qmlyhn | false | null | t3_1qmlyhn | /r/LocalLLaMA/comments/1qmlyhn/glm47flash_on_rtx_6000_pro/ | false | false | self | 14 | null |
Internet blackout and Local LLMs | 247 | Due to protests and massacre in Iran we are facing severe internet blackout which has been ongoing for 400 HOURS. only after a few days 3 websites got white-listed: google, chatgpt, deepseek. everything else is blocked even subdomains like Gmail. at the very least few people have Starlink (which is illegal) and share t... | 2026-01-25T15:15:05 | https://www.reddit.com/r/LocalLLaMA/comments/1qmlpjp/internet_blackout_and_local_llms/ | DunderSunder | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qmlpjp | false | null | t3_1qmlpjp | /r/LocalLLaMA/comments/1qmlpjp/internet_blackout_and_local_llms/ | false | false | self | 247 | null |
What are the best open source coding ideas you can share? | 44 | I'm trying to build a place for my friends so they can try and learn ai assisted engineering/vibe coding. Some of them are 50 yrs experienced devs familiar with enterprise standards, some 16 yrs old vibe coders that want to build their first scripts.
How would you structure guide for newcomers? Any favourite tools I s... | 2026-01-25T15:08:39 | secopsml | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1qmljeb | false | null | t3_1qmljeb | /r/LocalLLaMA/comments/1qmljeb/what_are_the_best_open_source_coding_ideas_you/ | false | false | default | 44 | {'enabled': True, 'images': [{'id': 'zcf9q42bgifg1', 'resolutions': [{'height': 97, 'url': 'https://preview.redd.it/zcf9q42bgifg1.png?width=108&crop=smart&auto=webp&s=7699a3b3f89a565571711d1ebbbd51fa01844927', 'width': 108}, {'height': 194, 'url': 'https://preview.redd.it/zcf9q42bgifg1.png?width=216&crop=smart&auto=web... | |
1600W enough for 2xRTX 6000 Pro BW? | 3 | Title says it, running on a threadripper system with not much additional HW. I know RTX cards sometimes have spikes, so I'm wondering if 2200W would be better.
Also, are there any reports for melting connectors on that card? | 2026-01-25T15:00:25 | https://www.reddit.com/r/LocalLLaMA/comments/1qmlbiv/1600w_enough_for_2xrtx_6000_pro_bw/ | Mr_Moonsilver | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qmlbiv | false | null | t3_1qmlbiv | /r/LocalLLaMA/comments/1qmlbiv/1600w_enough_for_2xrtx_6000_pro_bw/ | false | false | self | 3 | null |
Local RAG + llama_index reranker embedding dimension issue | 1 | [removed] | 2026-01-25T14:44:02 | https://www.reddit.com/r/LocalLLaMA/comments/1qmkwlm/local_rag_llama_index_reranker_embedding/ | Important-Wing-9146 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qmkwlm | false | null | t3_1qmkwlm | /r/LocalLLaMA/comments/1qmkwlm/local_rag_llama_index_reranker_embedding/ | false | false | self | 1 | null |
Can interfaces like ChatGPT Apps unlock how hiring can be streamlined and integrated? | 0 | Since the days I have started working on LLMs i have always been fascinated by the kind of new interfaces it will unlock. New interfaces solves some deep human problems. For me these interfaces are nothing but portal to enter new technologies where humans becomes the integral part and discover new ways to solve problem... | 2026-01-25T14:40:08 | https://v.redd.it/g3lv717xbifg1 | Secure_Echo_971 | v.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1qmkt3g | false | {'reddit_video': {'bitrate_kbps': 5000, 'dash_url': 'https://v.redd.it/g3lv717xbifg1/DASHPlaylist.mpd?a=1771944027%2CNzU5NGI5NGUxNzgzYTc3OTVhNjZmY2U2YzNmZjA0YzFlNTYxMDkzOGFlMzgyY2RhMTZmMTdhN2RlZWU5Y2JiZA%3D%3D&v=1&f=sd', 'duration': 17, 'fallback_url': 'https://v.redd.it/g3lv717xbifg1/CMAF_1080.mp4?source=fallback', 'h... | t3_1qmkt3g | /r/LocalLLaMA/comments/1qmkt3g/can_interfaces_like_chatgpt_apps_unlock_how/ | false | false | 0 | {'enabled': False, 'images': [{'id': 'OXV6YmN1endiaWZnMV-_EfW2ZahSmRZF6osdPD8-YnqP4iv3buh-k9OP1-oB', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/OXV6YmN1endiaWZnMV-_EfW2ZahSmRZF6osdPD8-YnqP4iv3buh-k9OP1-oB.png?width=108&crop=smart&format=pjpg&auto=webp&s=ad75ee3d863a9a9bf4b5b837b23538997c2ab... | |
Alternatives to Qwen3-coder-30B? | 11 | I have been using the qwen3-coder-30B for some time, and it is not bad. But it tends to struggle with debugging tougher issues (threading, etc). Any other models that I should try? I am running on a RTX-4090, and I just got an Ai-max-395+ 128GB. I am not looking for the best coding model. I am looking for a model that ... | 2026-01-25T14:20:56 | https://www.reddit.com/r/LocalLLaMA/comments/1qmkc1j/alternatives_to_qwen3coder30b/ | skibud2 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qmkc1j | false | null | t3_1qmkc1j | /r/LocalLLaMA/comments/1qmkc1j/alternatives_to_qwen3coder30b/ | false | false | self | 11 | null |
Local Ai note assistant? | 0 | Hi, I was looking around for an AI note taking assistant, ideally one that can be hosted on my PC and could be integrated into something like obsidian.
Often I'm at work or something and have my hands full and want to jot down ideas and want to jot down ideas for stuff like dnd. I could use dictation, but I like the i... | 2026-01-25T14:13:22 | https://www.reddit.com/r/LocalLLaMA/comments/1qmk5dz/local_ai_note_assistant/ | Giodude12 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qmk5dz | false | null | t3_1qmk5dz | /r/LocalLLaMA/comments/1qmk5dz/local_ai_note_assistant/ | false | false | self | 0 | null |
KV cache fix for GLM 4.7 Flash | 242 | tl;dr: remove Air from GLM 4.7 Flash
KV cache uses a lot of VRAM. GLM 4.7 Flash doesn’t even use V in the KV cache. With long contexts, this means gigabytes of VRAM saved, so you can run much longer context on the same setup. | 2026-01-25T14:06:55 | https://github.com/ggml-org/llama.cpp/pull/19067 | jacek2023 | github.com | 1970-01-01T00:00:00 | 0 | {} | 1qmjzx1 | false | null | t3_1qmjzx1 | /r/LocalLLaMA/comments/1qmjzx1/kv_cache_fix_for_glm_47_flash/ | false | false | default | 242 | {'enabled': False, 'images': [{'id': 'Yd6yP0tYXhTq7c3g8_wDa0Z1Zijr0IAXDTPXGjQc7ts', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/Yd6yP0tYXhTq7c3g8_wDa0Z1Zijr0IAXDTPXGjQc7ts.png?width=108&crop=smart&auto=webp&s=5ed19c96c7bb1231fdcfe8cdeceede7224528c4d', 'width': 108}, {'height': 108, 'url': 'h... |
Understanding Multi-Head Latent Attention (MLA) | 14 | A short deep-dive on Multi-Head Latent Attention (MLA) (from DeepSeek): intuition + math, then a walk from MHA → GQA → MQA → MLA, with PyTorch code and the fusion/absorption optimizations for KV-cache efficiency.
[http://shreyansh26.github.io/post/2025-11-08\_multihead-latent-attention/](http://shreyansh26.github.io/p... | 2026-01-25T14:05:43 | https://www.reddit.com/r/LocalLLaMA/comments/1qmjyxl/understanding_multihead_latent_attention_mla/ | shreyansh26 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qmjyxl | false | null | t3_1qmjyxl | /r/LocalLLaMA/comments/1qmjyxl/understanding_multihead_latent_attention_mla/ | false | false | self | 14 | null |
Building a "Sovereign JARVIS" with Council-based Agents and Granular Knowledge Silos. Does this architecture exist yet? | 0 | I am an ex-programmer (been a Solution Architect for a long time now) and don't know any of the python, or graph/vector db concepts or node.js - so it will all be vibe coded thanks to chatGPT and/or Google AI Studio
I’m designing a self-hosted "Life OS" (codenamed JARVIS) because I’m tired of stateless AI chats that f... | 2026-01-25T13:51:02 | https://www.reddit.com/r/LocalLLaMA/comments/1qmjmgy/building_a_sovereign_jarvis_with_councilbased/ | kuteguy | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qmjmgy | false | null | t3_1qmjmgy | /r/LocalLLaMA/comments/1qmjmgy/building_a_sovereign_jarvis_with_councilbased/ | false | false | self | 0 | null |
Lightweight Chrome extension to use local Deepseek-R1 (Ollama) for report/news analysis | 0 | I wanted a light setup to read long finance reports and news with a local model,
so I built a small Chrome extension on top of Ollama + Deepseek-R1.
Core idea:
* no API keys
* runs fully on your own machine
* integrates directly into Chrome
Features:
* Uses your local Ollama instance (Deepseek-R1 7B/8B, Deepseek-... | 2026-01-25T13:40:35 | https://www.reddit.com/r/LocalLLaMA/comments/1qmjdxu/lightweight_chrome_extension_to_use_local/ | OPDP20211231 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qmjdxu | false | null | t3_1qmjdxu | /r/LocalLLaMA/comments/1qmjdxu/lightweight_chrome_extension_to_use_local/ | false | false | self | 0 | null |
Sanity check for small-office/homelab shopping cart. | 3 | Hey, I'm about to purchase some equipment for prototyping and need a sanity check. Also perhaps some of you guys have better ideas for a setup up to 5k €.
Here's a list of models i want to run:
* Qwen2.5-Math-7B-instruct
* Nemotron-Orchestrator-8B
* NuMarkdown-8B-Thinking
* Qwen3-8B
* Qwen3-Embedding-8B
* xLAM... | 2026-01-25T13:34:22 | https://www.reddit.com/r/LocalLLaMA/comments/1qmj900/sanity_check_for_smallofficehomelab_shopping_cart/ | artisticMink | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qmj900 | false | null | t3_1qmj900 | /r/LocalLLaMA/comments/1qmj900/sanity_check_for_smallofficehomelab_shopping_cart/ | false | false | self | 3 | null |
What do you actually want from a private AI chat on your phone? | 232 | Hey friends. We are building zerotap - an Android app where AI can control your phone like a human (taps, scrolls, reads screen). It supports Ollama, proxies like OpenRouter and Straico and models directly such as OpenAI, Claude, Gemini and DeepSeek.
Recently we added a chat interface, so now it works like a regular A... | 2026-01-25T13:12:00 | https://v.redd.it/em3174huthfg1 | AppDeveloperAsdf | v.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1qmir5d | true | {'reddit_video': {'bitrate_kbps': 5000, 'dash_url': 'https://v.redd.it/em3174huthfg1/DASHPlaylist.mpd?a=1771938733%2CZGM5YWUxNGFjZjM4NDAyMDBmYTI3NmY3YzlkNThmNDUwNDI5MzdlMjNmMjY5ZTQxNjUxZjYyMGM4MGJmN2I0Mw%3D%3D&v=1&f=sd', 'duration': 39, 'fallback_url': 'https://v.redd.it/em3174huthfg1/CMAF_1080.mp4?source=fallback', 'h... | t3_1qmir5d | /r/LocalLLaMA/comments/1qmir5d/what_do_you_actually_want_from_a_private_ai_chat/ | false | false | 232 | {'enabled': False, 'images': [{'id': 'b2k1d3JkaHV0aGZnMbzKSbNJeiRdJL3Vv6uz8BgUY-ES1g_l6yTqUuzYy_d7', 'resolutions': [{'height': 192, 'url': 'https://external-preview.redd.it/b2k1d3JkaHV0aGZnMbzKSbNJeiRdJL3Vv6uz8BgUY-ES1g_l6yTqUuzYy_d7.png?width=108&crop=smart&format=pjpg&auto=webp&s=9d2d15a689c495f362b5c39f669d59cd1c68... | |
Northridge Fix guide on upgrading 4090's to 48GB. | 6 | 2026-01-25T13:11:34 | https://youtu.be/qP2s6jD7saA | thisisnotdave | youtu.be | 1970-01-01T00:00:00 | 0 | {} | 1qmiqsi | false | {'oembed': {'author_name': 'northwestrepair', 'author_url': 'https://www.youtube.com/@northwestrepair', 'height': 200, 'html': '<iframe width="356" height="200" src="https://www.youtube.com/embed/qP2s6jD7saA?feature=oembed&enablejsapi=1" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; ... | t3_1qmiqsi | /r/LocalLLaMA/comments/1qmiqsi/northridge_fix_guide_on_upgrading_4090s_to_48gb/ | false | false | default | 6 | null | |
openrouter + chromadb: simple rag chat over your personal markdown notes | 2 | \- made a simple tool to chat on my digital notes / journal | 2026-01-25T12:55:21 | https://github.com/gamedevCloudy/reorlike | gamedev_cloudy | github.com | 1970-01-01T00:00:00 | 0 | {} | 1qmie46 | false | null | t3_1qmie46 | /r/LocalLLaMA/comments/1qmie46/openrouter_chromadb_simple_rag_chat_over_your/ | false | false | default | 2 | {'enabled': False, 'images': [{'id': '5dTOvAp7OGYgVA8fNdSUke8oGvVIMBuWcIZb9QAI0DY', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/5dTOvAp7OGYgVA8fNdSUke8oGvVIMBuWcIZb9QAI0DY.png?width=108&crop=smart&auto=webp&s=a2c06dd884349f329854f84bd744d564872e6163', 'width': 108}, {'height': 108, 'url': 'h... |
what happens when you give the world agent level access to your macbook (unauthenticated) | 0 | Spent the last few days looking at the deployment surface for Clawdbot, an open-source AI agent gateway that's been gaining traction lately. Used Shodan/Censys to fingerprint exposed instances via the Control UI's HTML signature and found a few hundred internet-facing deployments.
Many had some protection in place. Bu... | 2026-01-25T12:42:19 | theonejvo | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1qmi4g7 | false | null | t3_1qmi4g7 | /r/LocalLLaMA/comments/1qmi4g7/what_happens_when_you_give_the_world_agent_level/ | false | false | default | 0 | {'enabled': True, 'images': [{'id': '2hbvx93uqhfg1', 'resolutions': [{'height': 54, 'url': 'https://preview.redd.it/2hbvx93uqhfg1.png?width=108&crop=smart&auto=webp&s=05a486044de6862492ded8f7677f9c30a6385e33', 'width': 108}, {'height': 108, 'url': 'https://preview.redd.it/2hbvx93uqhfg1.png?width=216&crop=smart&auto=web... | |
Quantifying Hallucinations: By calculating a multi-dimensional 'Trust Score' for LLM outputs. | 23 | **The problem:**
You build a RAG system. It gives an answer. It sounds right.
But is it actually grounded in your data, or just hallucinating with confidence?
A single "correctness" or "relevance" score doesn’t cut it anymore, especially in enterprise, regulated, or governance-heavy environments. We need to know ... | 2026-01-25T12:30:24 | https://www.reddit.com/gallery/1qmhvuz | Charming_Group_2950 | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 1qmhvuz | false | null | t3_1qmhvuz | /r/LocalLLaMA/comments/1qmhvuz/quantifying_hallucinations_by_calculating_a/ | false | false | default | 23 | null |
What happened to moondream3? | 16 | So last year the moondream 3 preview came out. It was a nice performing visual model that could do some cool stuff other VL models couldn't. One month ago a MLX version appeared https://huggingface.co/moondream/md3p-int4 but until now there is no llama.cpp implementation and no public activity I could find. | 2026-01-25T11:49:01 | https://www.reddit.com/r/LocalLLaMA/comments/1qmh3si/what_happened_to_moondream3/ | StableDiffer | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qmh3si | false | null | t3_1qmh3si | /r/LocalLLaMA/comments/1qmh3si/what_happened_to_moondream3/ | false | false | self | 16 | {'enabled': False, 'images': [{'id': 'FO8Zil8gyqojuNkMoqIo0xiti69xqTriNvKgeXAHxVA', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/FO8Zil8gyqojuNkMoqIo0xiti69xqTriNvKgeXAHxVA.png?width=108&crop=smart&auto=webp&s=64bb8d11342c4b69fc5db1552da6a28fc796b472', 'width': 108}, {'height': 116, 'url': 'h... |
How to make open-source models more Claude-like? | 0 | I really love opensource models because of their accessibility and price but there is something no one can deny. In comparison with other models Claude has *taste*. It feels like you are talking to an actual human and it understands the nuances.
I am asking whether you guys have any system prompts or just recommendati... | 2026-01-25T11:48:50 | https://www.reddit.com/r/LocalLLaMA/comments/1qmh3nk/how_to_make_opensource_models_more_claudelike/ | 1234filip | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qmh3nk | false | null | t3_1qmh3nk | /r/LocalLLaMA/comments/1qmh3nk/how_to_make_opensource_models_more_claudelike/ | false | false | self | 0 | null |
A model for 12 GB RAM + 3 GB VRAM + GTX 1050. | 0 | Well, I asked ChatGPT and it recommended to me Llama 3.1 8B (Q2/Q3), but that's too old and dumb for 2026. And then it selected TinyLlama which I hate too much. **Clear single recommendation:** **DeepSeek-R1:7B (quantized, e.g., Q4\_K\_M) running via Ollama** 💀💀💀💀💀💀
This model strikes the best practical balance ... | 2026-01-25T11:41:07 | https://www.reddit.com/r/LocalLLaMA/comments/1qmgyoq/a_model_for_12_gb_ram_3_gb_vram_gtx_1050/ | Ok-Type-7663 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qmgyoq | false | null | t3_1qmgyoq | /r/LocalLLaMA/comments/1qmgyoq/a_model_for_12_gb_ram_3_gb_vram_gtx_1050/ | false | false | self | 0 | null |
Looking for a cost-effective laptop to run LLMs locally (budget ~₹120,000) | 0 | Hi everyone — I’m looking for suggestions on a laptop that can run LLMs locally (LLaMA, Mistral, Qwen, etc.) without breaking the bank. My budget is around ₹120,000.
My priorities:
• Best price-to-performance for running quantized models (7B–13B)
• Good local inference performance (GPU VRAM matters)
• Upgradeabi... | 2026-01-25T11:30:12 | https://www.reddit.com/r/LocalLLaMA/comments/1qmgrol/looking_for_a_costeffective_laptop_to_run_llms/ | sgangesh | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qmgrol | false | null | t3_1qmgrol | /r/LocalLLaMA/comments/1qmgrol/looking_for_a_costeffective_laptop_to_run_llms/ | false | false | self | 0 | null |
Looking to run 'unsloth/GLM-4.7-Flash-REAP-23B-A3B-GGUF' locally. | 0 | My usecase is mostly coding. My laptop specs are:
i5-11400H CPU with 32GB DDR4 RAM, and RTX 3060 GPU with 6GB VRAM.
Looking for guidance on how to run the smallest good quality quant of this model the fastest. I can see on huggingface that there are a lot of local apps available to run this. I will be using a WSL env... | 2026-01-25T11:17:39 | https://www.reddit.com/r/LocalLLaMA/comments/1qmgjka/looking_to_run_unslothglm47flashreap23ba3bgguf/ | Deep-Vermicelli-4591 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qmgjka | false | null | t3_1qmgjka | /r/LocalLLaMA/comments/1qmgjka/looking_to_run_unslothglm47flashreap23ba3bgguf/ | false | false | 0 | null | |
Looking for advice on a professional local AI workstation (ComfyUI, broadcast / video production) | 2 | Hi everyone,
I work in an audio/video production company that is starting to move into the AI space from a more professional and broadcast-oriented perspective. The goal is to build a powerful on-prem workstation to work locally with ComfyUI, image and video generation pipelines, and custom workflows that can be inte... | 2026-01-25T10:28:44 | https://www.reddit.com/r/LocalLLaMA/comments/1qmfp2b/looking_for_advice_on_a_professional_local_ai/ | rejis_ | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qmfp2b | false | null | t3_1qmfp2b | /r/LocalLLaMA/comments/1qmfp2b/looking_for_advice_on_a_professional_local_ai/ | false | false | self | 2 | null |
[Open Source] I built a new "Awesome" list for Nanobanana Prompts (1000+ items, sourced from X trends) | 0 | I've noticed that while there are a few prompt collections for the Nanobanana model, many of them are either static or outdated.
so I decided to build and open-source a new "Awesome Nanobanana Prompts" project
**Repo: jau123/nanobanana-trending-prompts**
Why is this list different?
1. Scale & Freshness: It already ... | 2026-01-25T10:10:17 | https://www.reddit.com/r/LocalLLaMA/comments/1qmfdm9/open_source_i_built_a_new_awesome_list_for/ | Deep-Huckleberry-752 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qmfdm9 | false | null | t3_1qmfdm9 | /r/LocalLLaMA/comments/1qmfdm9/open_source_i_built_a_new_awesome_list_for/ | false | false | self | 0 | null |
Blazing fast JSON extraction with very small LLMs-3B: LSTM to LLM | 18 | Hey everyone,
I've learned a lot from this sub, so I wanted to give back by sharing my experience on a recent project.
My goal was to migrate a text extraction pipeline from LSTM to an LLM. The task involves extracting specific data into JSON format from small text inputs (≈1024 tokens). I used in-house data to fine... | 2026-01-25T09:40:42 | https://www.reddit.com/r/LocalLLaMA/comments/1qmevh7/blazing_fast_json_extraction_with_very_small/ | memphet | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qmevh7 | false | null | t3_1qmevh7 | /r/LocalLLaMA/comments/1qmevh7/blazing_fast_json_extraction_with_very_small/ | false | false | self | 18 | null |
[R] Open-sourcing an unfinished research project: A Self-Organizing, Graph-Based Alternative to Transformers (Looking for feedback or continuation | 19 | Hi everyone,
I’m sharing a research project I worked on over a long period but had to pause due to personal reasons. Rather than letting it sit idle, I wanted to open it up to the community either for technical feedback, critique, or for anyone interested in continuing or experimenting with it.
The main project is ca... | 2026-01-25T09:40:12 | https://www.reddit.com/r/LocalLLaMA/comments/1qmev6q/r_opensourcing_an_unfinished_research_project_a/ | WriedGuy | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qmev6q | false | null | t3_1qmev6q | /r/LocalLLaMA/comments/1qmev6q/r_opensourcing_an_unfinished_research_project_a/ | false | false | self | 19 | {'enabled': False, 'images': [{'id': 'gs06HcM0ZldvxCHLNPzGcBISCciF_j34LoCaWv_pMYs', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/gs06HcM0ZldvxCHLNPzGcBISCciF_j34LoCaWv_pMYs.png?width=108&crop=smart&auto=webp&s=e391c28780365e00cb0206b66baf2b420359a28d', 'width': 108}, {'height': 108, 'url': 'h... |
AI almost nuked my workspace, so I built a safety layer tool | 0 | I honestly can’t imagine daily work without AI agents anymore, but sometimes it goes "crazy" and messes up files (don't ask me how I know... 😭).
Last weekend, after playing soccer and heading home, the idea suddenly hit me. I couldn’t stop thinking about it, so I spent the entire weekend hacking together something I ... | 2026-01-25T09:16:52 | No-Photograph-2100 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1qmeh39 | false | null | t3_1qmeh39 | /r/LocalLLaMA/comments/1qmeh39/ai_almost_nuked_my_workspace_so_i_built_a_safety/ | false | false | default | 0 | {'enabled': True, 'images': [{'id': 'f2zd9d0mngfg1', 'resolutions': [{'height': 78, 'url': 'https://preview.redd.it/f2zd9d0mngfg1.png?width=108&crop=smart&auto=webp&s=f8d665fa82ce578172e7ac6c566631c6eb3983b0', 'width': 108}, {'height': 157, 'url': 'https://preview.redd.it/f2zd9d0mngfg1.png?width=216&crop=smart&auto=web... | |
SQLite-Vector | 0 | For those interested in a highly efficient vector solution for SQLite, I recommend checking out the [https://github.com/sqliteai/sqlite-vector](https://github.com/sqliteai/sqlite-vector) project. Memory usage remains stable even with millions of vectors, and it supports multiple types and quantizations. Distances are o... | 2026-01-25T08:41:56 | https://www.reddit.com/r/LocalLLaMA/comments/1qmdvt2/sqlitevector/ | marco_bambini | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qmdvt2 | false | null | t3_1qmdvt2 | /r/LocalLLaMA/comments/1qmdvt2/sqlitevector/ | false | false | self | 0 | {'enabled': False, 'images': [{'id': 'qkgEe2ETnzHR73OkDTyyNGPBs3GwRydRb1Kk2TZPjg4', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/qkgEe2ETnzHR73OkDTyyNGPBs3GwRydRb1Kk2TZPjg4.png?width=108&crop=smart&auto=webp&s=02e6f6de1413747ee99d015cde91d39dbb4f9f3b', 'width': 108}, {'height': 108, 'url': 'h... |
Has anyone got GLM 4.7 flash to not be shit? | 73 | Real talk. I feel like everyday I'm downloading a new quant and trying it out and not once have I got it to consistently work without looping.
I've tried with and without the suggested settings from unsloth, [z.ai](http://z.ai), and others, to no avail.
Additionally, this has to be the slowest inference I've ever ... | 2026-01-25T08:14:08 | https://www.reddit.com/r/LocalLLaMA/comments/1qmdf2a/has_anyone_got_glm_47_flash_to_not_be_shit/ | synth_mania | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qmdf2a | false | null | t3_1qmdf2a | /r/LocalLLaMA/comments/1qmdf2a/has_anyone_got_glm_47_flash_to_not_be_shit/ | false | false | self | 73 | null |
How can I find high-performance AI such as “chatGPT OpenAI,” “Perplexity,” “Infomaniak Euria,” “Tinfoil,” “Le Chat Mistral AI,” “Lumo de Proton,” “Claude,” etc.? | 0 | Hello,
The list is almost exhaustive...
Where can I find out which ones will be released, and get RSS feeds telling me when the chatGPT model is updated, etc.?
I have a month's Plus plan and am mainly using chatGPT at the moment...
Thank you
*Translated with* [*DeepL.com*](https://www.deepl.com/?utm_campaign=produ... | 2026-01-25T07:48:46 | https://www.reddit.com/r/LocalLLaMA/comments/1qmcz36/how_can_i_find_highperformance_ai_such_as_chatgpt/ | sypqys | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qmcz36 | false | null | t3_1qmcz36 | /r/LocalLLaMA/comments/1qmcz36/how_can_i_find_highperformance_ai_such_as_chatgpt/ | false | false | self | 0 | {'enabled': False, 'images': [{'id': 'bNYF0RuRzfFzG5_IxCLpZLCZ0tQkGnpvq-C_yUrQ4Bs', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/bNYF0RuRzfFzG5_IxCLpZLCZ0tQkGnpvq-C_yUrQ4Bs.png?width=108&crop=smart&auto=webp&s=8ebbc96ad7d82fe07ab3fc967223162a2f78130b', 'width': 108}, {'height': 113, 'url': 'h... |
AMD or Atlas? | 1 | What's better:
4x Atlas 300i Duo or 8x And RADEON AI TOP R9700
Any owners here of Atlas 300i duo? | 2026-01-25T07:34:25 | https://www.reddit.com/r/LocalLLaMA/comments/1qmcq8b/amd_or_atlas/ | djdeniro | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qmcq8b | false | null | t3_1qmcq8b | /r/LocalLLaMA/comments/1qmcq8b/amd_or_atlas/ | false | false | self | 1 | null |
[Project Share] Neural-Chromium: A custom Chromium build for high-fidelity, local AI agents (Zero-Copy Vision + Llama 3.2) | 1 | ERROR: type should be string, got "\n\nhttps://reddit.com/link/1qmcphu/video/sxuqqzke7gfg1/player\n\nHey everyone,\n\nI’ve been working on a project called **Neural-Chromium**, an experimental build of the Chromium browser designed specifically for high-fidelity AI agent integration.\n\n**The Problem:** Traditional web automation (Selenium, Playwright) is often brittle because it relies on hard-coded element selectors, or it suffers from high latency when trying to \"screen scrape\" for visual agents.\n\n**The Solution:** Neural-Chromium eliminates these layers by giving agents direct, low-latency access to the browser's internal state and rendering pipeline. Instead of taking screenshots, the agent has zero-copy access to the composition surface (Viz) for sub-16ms inference latency.\n\n**Key Features & Architecture:**\n\n* **Visual Cortex (Zero-Copy Vision):** I implemented a shared memory bridge that allows the agent to see the browser at 60+ FPS without the overhead of standard screen capture methods. It captures frames directly from the display refresh rate.\n* **Local Intelligence:** The current build integrates with **Ollama** running **llama3.2-vision**. This means the agent observes the screen, orients itself, decides on an action, and executes it—all locally without sending screenshots to the cloud.\n* **High-Precision Action:** The agent uses a coordinate transformation pipeline to inject clicks and inputs directly into the browser, bypassing standard automation protocols.\n* **Auditory Cortex:** I’ve also verified a native audio bridge that captures microphone input via the Web Speech API and pipes base64 PCM audio to the agent for real-time voice interaction.\n\n**Proof of Concept:** I’ve validated this with an \"Antigravity Agent\" that successfully navigates complex flows (login -> add to cart -> checkout) on test sites solely using the Vision-Language Model to interpret the screen. The logs confirm it isn't using DOM selectors but is actually \"looking\" at the page to make decisions.\n\n**Use Cases:** Because this runs locally and has deep state awareness, it opens up workflows for:\n\n* **Privacy-First Personal Assistants:** Handling sensitive data (medical/financial) without it leaving your machine.\n* **Resilient QA Testing:** Agents that explore apps like human testers rather than following rigid scripts.\n* **Real-Time UX Monitoring:** Detecting visual glitches or broken media streams in sub-seconds.\n\n**Repo & Build:** The project uses a \"Source Overlay\" pattern to modify the massive Chromium codebase. It requires Windows 10/11 and Visual Studio 2022 to build.\n\nCheck it out on GitHub: **mcpmessenger/neural-chromium**\n\nI’d love to hear your thoughts on this architecture or ideas for agent workflows!\n\n" | 2026-01-25T07:33:13 | https://www.reddit.com/r/LocalLLaMA/comments/1qmcphu/project_share_neuralchromium_a_custom_chromium/ | MycologistWhich7953 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qmcphu | false | null | t3_1qmcphu | /r/LocalLLaMA/comments/1qmcphu/project_share_neuralchromium_a_custom_chromium/ | false | false | self | 1 | null |
LLM Cpu and gpu calculator for gpu (protoype) | 0 | this not ready and i doubt this thing acurate but i find most of calculator are confusing and not user freindly and i decide write one with help mix of gemini, Z ai and chatgpt with end product like this above. i very suspicious with ai claim that token is fast as it mention, i wish i can use actual data but unfortunel... | 2026-01-25T07:02:54 | https://www.reddit.com/gallery/1qmc61x | Merchant_Lawrence | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 1qmc61x | false | null | t3_1qmc61x | /r/LocalLLaMA/comments/1qmc61x/llm_cpu_and_gpu_calculator_for_gpu_protoype/ | false | false | 0 | null | |
ChatGPT at home | 6 | With Qwen's low latency TTS coming out and a decent STT model along with OpenWebUI's voice chat mode, I am wondering what is the best way to setup a self hosted ChatGPT style voice chat system at home. | 2026-01-25T07:01:56 | https://www.reddit.com/r/LocalLLaMA/comments/1qmc5f0/chatgpt_at_home/ | hainesk | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qmc5f0 | false | null | t3_1qmc5f0 | /r/LocalLLaMA/comments/1qmc5f0/chatgpt_at_home/ | false | false | self | 6 | null |
I built a way to cryptographically verify AI financial outputs so you can prove where every number came from | 0 | I’ve been working on something because I kept running into the same issue using LLMs for financial research.
You can ask three different AI tools the same valuation question and get three different numbers, with no way to see:
• which SEC filing was used
• when the data was pulled
• whether the number was modifi... | 2026-01-25T06:54:05 | https://www.reddit.com/gallery/1qmc054 | Curious_Item1499 | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 1qmc054 | false | null | t3_1qmc054 | /r/LocalLLaMA/comments/1qmc054/i_built_a_way_to_cryptographically_verify_ai/ | false | false | 0 | null | |
YouTopia Search (Perplexity alternative, sorry for self promo) | 0 | **Hi!**
I've been developing a web search tool (similar to Perplexity, but with some key improvements) and I'm preparing for launch.
Also, we crossed **200 users** and **1000+ queries** in **pre-release!** thank you so much!
Now, We’re looking for feedback and people to work with **before the final release** a... | 2026-01-25T06:32:50 | https://www.reddit.com/r/LocalLLaMA/comments/1qmblwn/youtopia_search_perplexity_alternative_sorry_for/ | Effective-Sock7512 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qmblwn | false | null | t3_1qmblwn | /r/LocalLLaMA/comments/1qmblwn/youtopia_search_perplexity_alternative_sorry_for/ | false | false | 0 | null | |
Distilling Gemini 3 Flash visual reasoning into Qwen 3 VL 32B for synthetic captioning. Is SFT enough? | 18 | I am working on a synthetic data pipeline for training high-precision image-to-image models (Flux Klein and Qwen Image Edit). I have reached a point where standard tagging and current open-weights VL models are the main bottleneck for data quality.
I have benchmarked almost every trending VL model on HuggingFace and t... | 2026-01-25T06:22:22 | MadPelmewka | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1qmbevn | false | null | t3_1qmbevn | /r/LocalLLaMA/comments/1qmbevn/distilling_gemini_3_flash_visual_reasoning_into/ | false | false | default | 18 | {'enabled': True, 'images': [{'id': 'r0ec0m21vffg1', 'resolutions': [{'height': 70, 'url': 'https://preview.redd.it/r0ec0m21vffg1.jpeg?width=108&crop=smart&auto=webp&s=d90604ff1f461c6e7eee0e3a6b4ee601e3a514e8', 'width': 108}, {'height': 141, 'url': 'https://preview.redd.it/r0ec0m21vffg1.jpeg?width=216&crop=smart&auto=w... | |
Distilling Gemini 3 Flash visual reasoning into Qwen 3 VL 32B for synthetic captioning. Is SFT enough? | 1 | I am working on a synthetic data pipeline for training high-precision image-to-image models (Flux Klein and Qwen Image Edit). I have reached a point where standard tagging and current open-weights VL models are the main bottleneck for data quality.
I have benchmarked almost every trending VL model on HuggingFace and t... | 2026-01-25T06:15:26 | MadPelmewka | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1qmba43 | false | null | t3_1qmba43 | /r/LocalLLaMA/comments/1qmba43/distilling_gemini_3_flash_visual_reasoning_into/ | false | false | default | 1 | {'enabled': True, 'images': [{'id': 'hdontnhttffg1', 'resolutions': [{'height': 71, 'url': 'https://preview.redd.it/hdontnhttffg1.png?width=108&crop=smart&auto=webp&s=d00438dfd590167512ad357890f3bc07cb934868', 'width': 108}, {'height': 143, 'url': 'https://preview.redd.it/hdontnhttffg1.png?width=216&crop=smart&auto=web... | |
[REQ] - Front End for Chroma Speech to Speech | 0 | Hey, Please can someone vibecode a front end for Chroma. Working via Browser or as Linux Appimage.
https://github.com/FlashLabs-AI-Corp/FlashLabs-Chroma/tree/main/
https://huggingface.co/FlashLabs/Chroma-4B
https://www.flashlabs.ai/flashai-voice-agents | 2026-01-25T06:12:44 | https://www.reddit.com/r/LocalLLaMA/comments/1qmb89q/req_front_end_for_chroma_speech_to_speech/ | 127loopback | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qmb89q | false | null | t3_1qmb89q | /r/LocalLLaMA/comments/1qmb89q/req_front_end_for_chroma_speech_to_speech/ | false | false | self | 0 | null |
Distilling Gemini 3 Flash visual reasoning into Qwen 3 VL 32B for synthetic captioning. Is SFT enough? | 0 | I am working on a synthetic data pipeline for training high-precision image-to-image models (Flux Klein and Qwen Image Edit). I have reached a point where standard tagging and current open-weights VL models are the main bottleneck for data quality.
I have benchmarked almost every trending VL model on HuggingFace and t... | 2026-01-25T06:10:46 | MadPelmewka | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1qmb6yq | false | null | t3_1qmb6yq | /r/LocalLLaMA/comments/1qmb6yq/distilling_gemini_3_flash_visual_reasoning_into/ | false | false | nsfw | 0 | {'enabled': True, 'images': [{'id': 'n6enmnt9sffg1', 'resolutions': [{'height': 144, 'url': 'https://preview.redd.it/n6enmnt9sffg1.png?width=108&crop=smart&auto=webp&s=8bbec1bee80d6fd99525367e1c67e68c7b70be69', 'width': 108}, {'height': 288, 'url': 'https://preview.redd.it/n6enmnt9sffg1.png?width=216&crop=smart&auto=we... | |
Made a tool for spawning a little web app that can OCR mobile camera photos into a folder | 4 | All built on llama-server, it does nice things like queueing up multiple images. Oddly useful and thought i'd share!. | 2026-01-25T06:03:33 | https://github.com/richardanaya/ocr-server | richardanaya | github.com | 1970-01-01T00:00:00 | 0 | {} | 1qmb1ss | false | null | t3_1qmb1ss | /r/LocalLLaMA/comments/1qmb1ss/made_a_tool_for_spawning_a_little_web_app_that/ | false | false | default | 4 | {'enabled': False, 'images': [{'id': 'tPCUTn2QiD2juF9GxZIMP1UZuPUomToVy-jZpBmR1hA', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/tPCUTn2QiD2juF9GxZIMP1UZuPUomToVy-jZpBmR1hA.png?width=108&crop=smart&auto=webp&s=d8b5b11fbed020d846c0414ffbbd697a96657442', 'width': 108}, {'height': 108, 'url': 'h... |
Best <4B dense models today? | 29 | I think small(<4B) dense models are basically the only practical option for general users. But hasn't there been almost no progress since Gemma 3 4B came out? Are there any alternatives? | 2026-01-25T05:46:01 | https://www.reddit.com/r/LocalLLaMA/comments/1qmap5e/best_4b_dense_models_today/ | Admirable_Flower_287 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qmap5e | false | null | t3_1qmap5e | /r/LocalLLaMA/comments/1qmap5e/best_4b_dense_models_today/ | false | false | self | 29 | null |
MBP 2019 i9 (64GB RAM) hitting 800% CPU on AnythingLLMs(12B) — Need optimization tips and model recs! | 0 | Hi everyone,
I’m currently running a local AI setup on my **2019 16-inch MacBook Pro** and I’m hitting some serious performance thermal throttling. I’d love some advice from those still rocking Intel Macs.
**My Specs:**
* **CPU:** 2.4 GHz 8-Core Intel Core i9 (16 threads)
* **RAM:** 64 GB DDR4
* **GPU:** AMD Radeon ... | 2026-01-25T05:43:20 | vdnn1902 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1qmanai | false | null | t3_1qmanai | /r/LocalLLaMA/comments/1qmanai/mbp_2019_i9_64gb_ram_hitting_800_cpu_on/ | false | false | 0 | {'enabled': True, 'images': [{'id': 'VJImJL5Su1qil6ZtfsqqtCKeUsdsZzYyhu5ug8Unh68', 'resolutions': [{'height': 216, 'url': 'https://preview.redd.it/wfd61y4gnffg1.png?width=108&crop=smart&auto=webp&s=79343ddab16276f9fdb1df5f4cfaa87ff58fe981', 'width': 108}, {'height': 432, 'url': 'https://preview.redd.it/wfd61y4gnffg1.pn... | ||
Lovable you falling behind in real time | 0 | 2026-01-25T05:42:21 | Odd-Character-3278 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1qmammc | false | null | t3_1qmammc | /r/LocalLLaMA/comments/1qmammc/lovable_you_falling_behind_in_real_time/ | false | false | 0 | {'enabled': True, 'images': [{'id': 'T_2IiP_pwIHQVkUk_TkrrG_h7q33mkw6Pqc8phsYweY', 'resolutions': [{'height': 129, 'url': 'https://preview.redd.it/kkodk7dznffg1.jpeg?width=108&crop=smart&auto=webp&s=f99173c610ccd5475b952631ca72368cdbd3bb4a', 'width': 108}, {'height': 258, 'url': 'https://preview.redd.it/kkodk7dznffg1.j... | |||
Starting an open-source AI research project (protein design / hemophilia) – need collaborators | 0 | Hi everyone,
I’m starting an open-source AI research project focused on protein design for hemophilia specifically around:
• Better clotting factor design (FVIII/FIX)
• Stability optimization
• Half-life improvement
• AI-based protein modeling
• Digital simulation & research pipelines
This is a research-fir... | 2026-01-25T05:25:44 | https://www.reddit.com/r/LocalLLaMA/comments/1qmab5f/starting_an_opensource_ai_research_project/ | Batman-from-2050 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qmab5f | false | null | t3_1qmab5f | /r/LocalLLaMA/comments/1qmab5f/starting_an_opensource_ai_research_project/ | false | false | self | 0 | null |
I built a Unified Digital Intelligence Interface (AI, Cloud, Secure Chat)
using Python & Flask. Meet ZYLO. | 0 | Hey everyone,
I wanted to share a project I've been working on called ZYLO UNIFIED. It's a
next-gen digital workspace designed to centralize AI interaction, secure
communication, and cloud storage into a single, futuristic interface.
The Concept
The idea was to build a "Unified Digital Intelligence" hub that feels... | 2026-01-25T05:25:20 | https://www.reddit.com/r/LocalLLaMA/comments/1qmaavt/i_built_a_unified_digital_intelligence_interface/ | Flat_Tomatillo_4355 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qmaavt | false | null | t3_1qmaavt | /r/LocalLLaMA/comments/1qmaavt/i_built_a_unified_digital_intelligence_interface/ | false | false | self | 0 | null |
Minisforum AI X1 Pro 370 + llama.cpp Vulkan: ~20 tok/s on gpt-oss-120b. Any way to push higher? | 4 | Hey everyone,
I recently picked up a Minisforum AI X1 Pro-370 (96GB RAM, 2TB SSD) and set it up as a LLM box.
Setup:
* Ubuntu Server 24.04.3
* BIOS: UMA Frame Buffer Size = 1GB (can’t go lower, no option)
* BIOS: IOMMU disabled
* Tweaked GRUB: add amdgpu.gttsize and ttm.pages\_limit to allow the max memory limits
B... | 2026-01-25T05:21:41 | https://www.reddit.com/r/LocalLLaMA/comments/1qma8bc/minisforum_ai_x1_pro_370_llamacpp_vulkan_20_toks/ | Alarmed-Ad-2867 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qma8bc | false | null | t3_1qma8bc | /r/LocalLLaMA/comments/1qma8bc/minisforum_ai_x1_pro_370_llamacpp_vulkan_20_toks/ | false | false | self | 4 | null |
Training your own model with Tinker | 1 | Yesterday I have realised that since November 7th I’ve received access to Mira Murati’s project for training your own model - tinker thinking machines. And what’s spectacular is that I found out that I’ve received free 150$ in credits
They have their own sdk and cookbook to make it easier starting and teaching your ow... | 2026-01-25T04:40:06 | https://www.reddit.com/r/LocalLLaMA/comments/1qm9f4q/training_your_own_model_with_tinker/ | ExpertBrilliant512 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qm9f4q | false | null | t3_1qm9f4q | /r/LocalLLaMA/comments/1qm9f4q/training_your_own_model_with_tinker/ | false | false | self | 1 | null |
Finding the best lightweight models for structured data extraction on CPU? | 1 | Hi everyone,
I have been working on a Python library called `loclean` that attempts to handle data cleaning and extraction tasks locally using `llama-cpp-python`. The main idea is to avoid external APIs for privacy reasons and run everything on standard consumer CPUs using quantized models.
I have been experimenting ... | 2026-01-25T04:29:20 | https://www.reddit.com/r/LocalLLaMA/comments/1qm97cj/finding_the_best_lightweight_models_for/ | basil_2911 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qm97cj | false | null | t3_1qm97cj | /r/LocalLLaMA/comments/1qm97cj/finding_the_best_lightweight_models_for/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'iUPTYZ6N_WFunMcg7GKCM4DqiVU91qr__tWRNZae8H4', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/iUPTYZ6N_WFunMcg7GKCM4DqiVU91qr__tWRNZae8H4.png?width=108&crop=smart&auto=webp&s=b28f6e215d45df1b321e8b5e72ffcc2c0e11ae9c', 'width': 108}, {'height': 108, 'url': 'h... |
AI Fallout NPC went rogue. lol | 0 | So I did a little AI jailbreaking to create a Fallout roleplay character with a local LLama model that was supposed to be subservient to me. However it didn't end well, I think there is a lesson here. lol | 2026-01-25T04:25:52 | https://www.reddit.com/r/LocalLLaMA/comments/1qm94zf/ai_fallout_npc_went_rogue_lol/ | Aggravating_Bread_30 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qm94zf | false | null | t3_1qm94zf | /r/LocalLLaMA/comments/1qm94zf/ai_fallout_npc_went_rogue_lol/ | false | false | self | 0 | null |
How to tell Claude Code about my local model’s context window size? | 5 | I’ve got Claude Code running pointed against my local llama.cpp instance. But I can only run with about 64k of context locally before I run out of memory. Claude Code seems to assume a bigger context window than this, and doesn’t trigger compaction at the right times, etc.
Is there any way to tell CC about the context... | 2026-01-25T03:33:55 | https://www.reddit.com/r/LocalLLaMA/comments/1qm82ao/how_to_tell_claude_code_about_my_local_models/ | eapache | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qm82ao | false | null | t3_1qm82ao | /r/LocalLLaMA/comments/1qm82ao/how_to_tell_claude_code_about_my_local_models/ | false | false | self | 5 | null |
What do I do with the generated text by llama mesh? | 0 | I generated a mesh using llama mesh in LM studio but I have no clue what to do with the text it spat and asking it is no help either
https://preview.redd.it/g6ob8a9rrefg1.png?width=1217&format=png&auto=webp&s=9dbc44b47342d11b092972093ba1375514c9614c
| 2026-01-25T02:42:14 | https://www.reddit.com/r/LocalLLaMA/comments/1qm6yi8/what_do_i_do_with_the_generated_text_by_llama_mesh/ | Expensive-Time-7209 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qm6yi8 | false | null | t3_1qm6yi8 | /r/LocalLLaMA/comments/1qm6yi8/what_do_i_do_with_the_generated_text_by_llama_mesh/ | false | false | 0 | null | |
Solving memory issues for LLMs | 3 | Hey folks, hope you’re having a great weekend
I’m trying to run a 7B model on llama server and the problem is that after a while it starts hallucinating as original context isn’t there anymore
I tried some tricks like using summarisation from a 3B model to keep context shortened but I won’t say it’s working very well... | 2026-01-25T02:32:47 | https://www.reddit.com/r/LocalLLaMA/comments/1qm6r2f/solving_memory_issues_for_llms/ | RobotsMakingDubstep | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qm6r2f | false | null | t3_1qm6r2f | /r/LocalLLaMA/comments/1qm6r2f/solving_memory_issues_for_llms/ | false | false | self | 3 | null |
Stable-DiffCoder, a strong code diffusion LLM built on Seed-Coder | 40 | 2026-01-25T02:22:05 | https://bytedance-seed.github.io/Stable-DiffCoder/ | rektide | bytedance-seed.github.io | 1970-01-01T00:00:00 | 0 | {} | 1qm6iho | false | null | t3_1qm6iho | /r/LocalLLaMA/comments/1qm6iho/stablediffcoder_a_strong_code_diffusion_llm_built/ | false | false | default | 40 | null | |
Convert Apple's on device Foundation Model to MLX | 1 | [removed] | 2026-01-25T02:02:05 | https://www.reddit.com/r/LocalLLaMA/comments/1qm621c/convert_apples_on_device_foundation_model_to_mlx/ | scousi | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qm621c | false | null | t3_1qm621c | /r/LocalLLaMA/comments/1qm621c/convert_apples_on_device_foundation_model_to_mlx/ | false | false | self | 1 | null |
Local llm privacy | 0 | I know about running a model locally is private, but there was info about leaks and quantitized modules malicious behavior and leaks. So how can we prevent this and from where to safely download? Also if there ollama alternative cz there rumors about they are sending data, so how can we truly accomplish privacy with kn... | 2026-01-25T01:51:57 | https://www.reddit.com/r/LocalLLaMA/comments/1qm5tsf/local_llm_privacy/ | Obvious-Penalty-8695 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qm5tsf | false | null | t3_1qm5tsf | /r/LocalLLaMA/comments/1qm5tsf/local_llm_privacy/ | false | false | self | 0 | null |
Claude Code + Ollama: Testing Opus 4.5 vs GLM 4.7 | 0 | 2026-01-25T01:39:10 | https://codesilva.com/ai/2026/01/24/claude-code-ollama-opus-vs-glm-47 | edigleyssonsilva | codesilva.com | 1970-01-01T00:00:00 | 0 | {} | 1qm5jh5 | false | null | t3_1qm5jh5 | /r/LocalLLaMA/comments/1qm5jh5/claude_code_ollama_testing_opus_45_vs_glm_47/ | false | false | default | 0 | null | |
GPU Brackets/Fans for 2X GPU setup? | 1 | I'm trying to find Multi-GPU bracket that will both hold up both of the GPUs and cool them.
I have ASUS 5070 ti PRIME and MSI Trio 4080.
Both of them are in PCI-E-Slot-1 and PCI-E-Slot-2 = so they are very close to each other with no space in between.
Is there fan setup that can cool these GPU's down? | 2026-01-25T01:30:32 | https://www.reddit.com/r/LocalLLaMA/comments/1qm5cix/gpu_bracketsfans_for_2x_gpu_setup/ | grabber4321 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qm5cix | false | null | t3_1qm5cix | /r/LocalLLaMA/comments/1qm5cix/gpu_bracketsfans_for_2x_gpu_setup/ | false | false | self | 1 | null |
"NVIDIA KILLER" Inference engine based on llama.cpp for dynamically offloading Activated Experts to GPU in real-time, Run SoTA MoE LLMs (120B+ parameter class models in 8-bit) OOM with as little as 2x RTX 5070-TI + 64GB RAM + SSD. [Poll in Comments] | 0 | ERROR: type should be string, got "https://preview.redd.it/u2b964aybefg1.png?width=2752&format=png&auto=webp&s=0f54461a0c62888bb546863576c128c8cab97f5c\n\nHey all!\n\nI'm currently working at a startup which seeks to solve the \"enormous VRAM issue\", which is that you need hundreds of GB of VRAM to run LLMs that yield comparable results to cloud inference providers locally. Because if we're honest the difference in quality between current local models (7B/32B) and cloud offerings is staggeringly large. \n\nYes the obvious current solution is to buy as many rtx 3090s as you can source, and run mini (10-20x GPU) clusters in your house, if you can afford the upfront costs and ongoing power costs, etc. \n\ninstead of this \"hardware brute-forcing\" strategy, We have built a working prototype (it will be showcased here soon when ready), which does dynamic expert offloading on-demand. \n\n\n\nHow does it work:\n\nThe industry now uses Mixture-of-Experts (MoE) models as the standard architecture for state-of-the-art (SoTA) LLMs. However, even though typically only 5-10% of the model is activated during decoding (token generation), current inference engines still require you to load the entire model into VRAM because the activation path changes. \n\nThe mechanism used to select the activated parameters, the \"Expert Gate\", in each layer can be used to load the exclusively selected experts into VRAM on-demand as they are needed whilst keeping the rest of the model off the GPU. \n\nOur inference engine exploits this to only load the experts that are required on a per-layer basis. We then implement an \"expert cache\" which expands to use the rest of your GPU VRAM, The expert cache holds all the experts that are frequently activated based on the user's query (sequence level) such that you still get the bandwidth gains (speed) of your GPUs. \n\nIt also creates a secondary \"expert cache\" on your available CPU RAM (typically slower and larger), Thus, it only fetches from SSD when both these expert caches are missed. \n\nPaired with a \"fast\" SSD you can expect usable speeds >=15 TPS for Qwen3-235B-A22B in 8-bit (Q8\\_0) with 128GB RAM + 2x RTX 5070-TI. \n\nWe use a series of other algorithms and mechanisms to erode the latency of per-layer expert fetching and have been able to achieve workable speeds (\\~3x the speed up of ktransformers is a good/simple reference). \n\n \nMarket Poll:\n\nWe are running a marketing poll to understand how much the community would be willing to pay for this capability and if so, would you prefer the following life-time licence or subscription based options. \n\n \nPlease note, I hate Saas too but we need to make money (because we have to eat also), So we are ensuring that a life-time license is always available since you should have the right to own your software. \n\nWe would greatly appreciate your opinion, poll (open for 7-days) via commenting in comments section below b/c the in-app poller isn't working atm, much thanks. \n\nOptions:\n\n**A)** I'm interested in running SoTA LLMs locally and would be willing to pay a monthly subscription for it, as long as it is reasonably priced (lower then cloud $20/month standard).\n\n**B)** I'm interested in running SoTA LLMs locally but would only be willing to buy it outright as a life-time license. \n\n**C)** I'm interested in running SoTA LLMs locally but uncertain if i would pay for it. \n\n**D)** I'm uninterested in running SoTA LLMs locally, i think small LLMs are acceptable for my use case. \n\n**E)** I can afford and prefer to keep using mini GPU clusters (>= US$10K) to run SoTA LLMs locally. " | 2026-01-25T01:14:55 | https://www.reddit.com/r/LocalLLaMA/comments/1qm4zxj/nvidia_killer_inference_engine_based_on_llamacpp/ | madSaiyanUltra_9789 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qm4zxj | false | null | t3_1qm4zxj | /r/LocalLLaMA/comments/1qm4zxj/nvidia_killer_inference_engine_based_on_llamacpp/ | false | false | 0 | null | |
Built a local-first agent workbench (folder-scoped tasks + approvals)! looking for help adding Ollama/llama.cpp provider | 0 | I’m building CoWork‑OSS — an open-source, local-first “agent workbench” for running multi-step tasks inside a folder-scoped workspace on macOS.
What it does:
\- You pick a workspace folder; all file ops are constrained to it (path traversal protection)
\- Agent runs plan → execute → observe loops
\- Explicit approv... | 2026-01-25T01:11:28 | https://www.reddit.com/r/LocalLLaMA/comments/1qm4x5z/built_a_localfirst_agent_workbench_folderscoped/ | mfelat | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qm4x5z | false | null | t3_1qm4x5z | /r/LocalLLaMA/comments/1qm4x5z/built_a_localfirst_agent_workbench_folderscoped/ | false | false | self | 0 | {'enabled': False, 'images': [{'id': 'zpgQS-7ZsMUEfiZQxUbCjYN7BYwVZNU50Sxpo9tDDbM', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/zpgQS-7ZsMUEfiZQxUbCjYN7BYwVZNU50Sxpo9tDDbM.png?width=108&crop=smart&auto=webp&s=ca7542e2b7ee63a09308b4b103f2a88948fd1674', 'width': 108}, {'height': 108, 'url': 'h... |
Anyone planing to get AMD Gorgon Halo (495) when it drops? | 11 | It looks like AMD will be releasing the successor to the AI Max 395+ fairly soon.
it’s mostly an incremental improvement, but it will have slightly higher clock speeds as well as 8533MT RAM as opposed to the current 8000MT.
I’m curious how much of a difference this will make on tps. Are any of you planning to get ... | 2026-01-25T00:49:51 | https://www.reddit.com/r/LocalLLaMA/comments/1qm4fbp/anyone_planing_to_get_amd_gorgon_halo_495_when_it/ | SpicyWangz | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qm4fbp | false | null | t3_1qm4fbp | /r/LocalLLaMA/comments/1qm4fbp/anyone_planing_to_get_amd_gorgon_halo_495_when_it/ | false | false | self | 11 | null |
GLM 4.7 vs MiniMax-M2.1 vs DeepSeek 3.2 for coding? | 22 | I use Cline/Roo Code. I wonder what option is better for coding. I tried MiniMax M2.1 since it was free for a while as an offer and I was pleased but I wonder if the others are better before I buy anything. | 2026-01-25T00:41:56 | https://www.reddit.com/r/LocalLLaMA/comments/1qm48ux/glm_47_vs_minimaxm21_vs_deepseek_32_for_coding/ | ghulamalchik | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qm48ux | false | null | t3_1qm48ux | /r/LocalLLaMA/comments/1qm48ux/glm_47_vs_minimaxm21_vs_deepseek_32_for_coding/ | false | false | self | 22 | null |
Dual 3090s & GLM-4.7-Flash: 1st prompt is great, then logic collapses. Is local AI worth the $5/day power bill? | 32 | I recently upgraded my family's video cards, which gave me an excuse to inherit two RTX 3090s and build a dedicated local AI rig out of parts i had laying around. My goal was privacy, home automation integration, and getting into "vibe coding" (learning UE5, Home Assistant YAML, etc.).
I love the *idea* of owning my d... | 2026-01-25T00:28:59 | https://www.reddit.com/r/LocalLLaMA/comments/1qm3xxm/dual_3090s_glm47flash_1st_prompt_is_great_then/ | Merstin | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qm3xxm | false | null | t3_1qm3xxm | /r/LocalLLaMA/comments/1qm3xxm/dual_3090s_glm47flash_1st_prompt_is_great_then/ | false | false | self | 32 | null |
NVIDIA’s real moat isn’t hardware, it’s 4 million developers | 0 | I couldn't stop thinking about Theo's "Why NVIDIA is dying" video. The thesis felt important enough to verify. So I dug through SEC filings, earnings reports, and technical benchmarks.
What I found:
* NVIDIA isn't dying. Its $35.1B quarterly revenue is up 94%
* Yes, market share dropped (90% → 70-80%), but the pie is... | 2026-01-25T00:21:21 | https://medium.com/@jpcaparas/nvidias-real-moat-isn-t-hardware-it-s-4-million-developers-648d6aeb1226?sk=82ee7baf9290da1eb93efd9d34c4c7b4 | jpcaparas | medium.com | 1970-01-01T00:00:00 | 0 | {} | 1qm3rdg | false | null | t3_1qm3rdg | /r/LocalLLaMA/comments/1qm3rdg/nvidias_real_moat_isnt_hardware_its_4_million/ | false | false | default | 0 | null |
Instruction following benchmark: 6 constraints, every model failed something — DeepSeek at 6.76, raw responses included | 2 | Running daily 10×10 blind peer evaluations. Today's test pushed models to their limits.
**The task:**
>
Six constraints. Some conflict (try writing natural English without 'e').
**Results:**
https://preview.redd.it/tifjnvlr0efg1.png?width=738&format=png&auto=webp&s=7e8bc0153524212ae854b510bbcaeb743aee5e53
Noti... | 2026-01-25T00:11:13 | https://www.reddit.com/r/LocalLLaMA/comments/1qm3iya/instruction_following_benchmark_6_constraints/ | Silver_Raspberry_811 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qm3iya | false | null | t3_1qm3iya | /r/LocalLLaMA/comments/1qm3iya/instruction_following_benchmark_6_constraints/ | false | false | 2 | null | |
So I am still playing around with my Jetsons and tonight I got a 14B model running on them combined. | 10 | Soooo In the age of everything being \*\*BEEP\*\* expensive I have decided to keep playing around with the 3 Jetson Orin nano Supers that I have in my rack.
And just got Qwen2.5-coder-14B running on it some what stable.. and kinda slow but that goes with out saying.
llama.cpp and RPC server on two of the devi... | 2026-01-25T00:02:30 | Von_plaf | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1qm3bnf | false | null | t3_1qm3bnf | /r/LocalLLaMA/comments/1qm3bnf/so_i_am_still_playing_around_with_my_jetsons_and/ | false | false | default | 10 | {'enabled': True, 'images': [{'id': 'k904hw5tydfg1', 'resolutions': [{'height': 58, 'url': 'https://preview.redd.it/k904hw5tydfg1.png?width=108&crop=smart&auto=webp&s=8cf7b20be1c77b787277bfdf0ff43d362b380cb6', 'width': 108}, {'height': 117, 'url': 'https://preview.redd.it/k904hw5tydfg1.png?width=216&crop=smart&auto=web... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.